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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Refugee
    -0.07
    (src
    -0.07
    _EMIT
    -0.07
     oltre
    -0.07
    资助
    -0.06
    pire
    -0.06
     Colleg
    -0.06
    _DECL
    -0.06
    wei
    -0.06
    POSITIVE LOGITS
    ****************************************************************
    0.07
    哿
    0.07
     hardness
    0.07
    痞
    0.07
    opathic
    0.07
    洛
    0.07
    ERCHANT
    0.07
     tournaments
    0.07
     powers
    0.07
    ﲪ
    0.07
    Act Density 0.001%

    No Known Activations