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

    Neuronpedia

    INDEX
    Explanations

    human discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    泺
    0.38
    ByDefault
    0.36
    প্রিম
    0.36
    鹜
    0.36
     वडिला
    0.35
    菒
    0.34
    popupIsOpen
    0.33
     caller
    0.32
     apellidos
    0.32
     opcoes
    0.32
    POSITIVE LOGITS
     human
    4.59
     Human
    4.19
    Human
    4.19
    human
    4.16
     челове
    3.95
     humans
    3.91
     HUMAN
    3.84
     인간
    3.78
    人类
    3.63
     Humans
    3.63
    Act Density 0.355%

    No Known Activations