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

    Neuronpedia

    INDEX
    Explanations

    confessions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itr
    -0.07
    ᴇ
    -0.07
    ROADCAST
    -0.07
    نتظر
    -0.07
     midway
    -0.07
     Arbeit
    -0.07
     itr
    -0.07
    -hour
    -0.07
     addons
    -0.07
    (att
    -0.06
    POSITIVE LOGITS
    קוס
    0.07
     bespoke
    0.07
    五星
    0.07
    _ten
    0.07
    мен
    0.07
    身份证
    0.06
    🏙
    0.06
    现金
    0.06
    �
    0.06
    👱
    0.06
    Act Density 0.003%

    No Known Activations