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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    がい
    -0.07
    ΑΛ
    -0.07
    گ
    -0.07
    _nv
    -0.07
    **:
    -0.06
    給
    -0.06
    Always
    -0.06
    TK
    -0.06
    まず
    -0.06
     알
    -0.06
    POSITIVE LOGITS
     message
    0.07
    ��
    0.06
     환
    0.06
     preacher
    0.06
    _operations
    0.06
    REGION
    0.06
    идента
    0.06
    Documents
    0.06
     inception
    0.06
     Permit
    0.06
    Act Density 0.002%

    No Known Activations