Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to locations or directional terms within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    location prefix followed by place/object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correa
    -0.37
     what
    -0.35
     jakim
    -0.35
    FirebaseAuth
    -0.33
    Romania
    -0.32
     graduación
    -0.31
     abstrato
    -0.31
    what
    -0.31
    所
    -0.31
    失
    -0.31
    POSITIVE LOGITS
     MainAxisSize
    0.80
     bedside
    0.73
     riverside
    0.71
    期刊论文
    0.68
     nahilalakip
    0.67
    حياته
    0.64
     Lakeside
    0.63
     CreateTagHelper
    0.63
     IBOutlet
    0.62
     beachfront
    0.62
    Act Density 0.006%

    No Known Activations