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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration and positive recognition

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

    admire, admirable, Adml, envy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nozze
    -0.45
    jsonwebtoken
    -0.44
    latLng
    -0.43
    LookAnd
    -0.43
    transQ
    -0.43
    Kali
    -0.42
    AuthContext
    -0.42
    oader
    -0.40
     gyhoeddwyd
    -0.40
     ISNI
    -0.39
    POSITIVE LOGITS
     admiration
    0.63
     admire
    0.60
     admired
    0.59
     admires
    0.55
     admiring
    0.54
     navideños
    0.53
    awtextra
    0.51
     CreateTagHelper
    0.50
     InputDecoration
    0.50
    佩服
    0.50
    Act Density 0.005%

    No Known Activations