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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _corner
    -0.06
     tiếng
    -0.06
    VarInsn
    -0.06
     patiently
    -0.06
     "="
    -0.06
     стало
    -0.06
     vydání
    -0.06
    elps
    -0.06
    _multiple
    -0.06
     ------
    -0.06
    POSITIVE LOGITS
    #plt
    0.07
    hashed
    0.07
     NUITKA
    0.06
    感
    0.06
    upon
    0.06
    HF
    0.06
    oci
    0.06
     В
    0.06
     viol
    0.06
     Civic
    0.06
    Act Density 0.007%

    No Known Activations