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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     życia
    -0.09
    _mappings
    -0.07
    Uno
    -0.07
    EMPLATE
    -0.07
     nada
    -0.07
     pública
    -0.07
     onMouse
    -0.07
    婆
    -0.07
     trông
    -0.07
    כוכב
    -0.06
    POSITIVE LOGITS
    "]->
    0.07
    }',↵
    0.07
    asco
    0.07
    弟
    0.07
     �
    0.06
     volley
    0.06
    ENCHMARK
    0.06
    бал
    0.06
     Iter
    0.06
    �
    0.06
    Act Density 0.165%

    No Known Activations