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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     recreation
    -0.06
    ロー
    -0.06
    (["
    -0.06
    ع
    -0.06
    PHONE
    -0.05
    SearchTree
    -0.05
    +"&
    -0.05
    ショ
    -0.05
     vines
    -0.05
    POSITIVE LOGITS
    currentTime
    0.07
     consolidated
    0.07
    _THRESHOLD
    0.07
     Mitarbeiter
    0.07
     jit
    0.06
     Jeans
    0.06
     slut
    0.06
     prescriptions
    0.06
     farmers
    0.06
    ovém
    0.06
    Act Density 0.001%

    No Known Activations