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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "F
    -0.07
    였
    -0.06
    Proveedor
    -0.06
    _MAIL
    -0.06
     repeatedly
    -0.06
    _board
    -0.06
     보면
    -0.06
    Lv
    -0.06
     Inst
    -0.06
    !==
    -0.06
    POSITIVE LOGITS
    xin
    0.07
     victories
    0.07
    �
    0.07
    lif
    0.06
    ibrate
    0.06
     ingredients
    0.06
    hist
    0.06
    lookup
    0.06
    обра�
    0.06
    Чер
    0.06
    Act Density 0.025%

    No Known Activations