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
    ']."
    -0.08
     Katy
    -0.07
    ]+"
    -0.07
     чер
    -0.07
    _Pro
    -0.07
     sesión
    -0.07
     MIL
    -0.06
    _prop
    -0.06
     cómo
    -0.06
    carbon
    -0.06
    POSITIVE LOGITS
     чист
    0.06
     firstName
    0.06
    wnd
    0.06
    Sig
    0.06
    PAD
    0.06
    (item
    0.06
    _REGEX
    0.06
     hedef
    0.06
    SmartPointer
    0.06
     heals
    0.06
    Act Density 0.000%

    No Known Activations