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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |max
    -0.07
     '_'
    -0.07
    _len
    -0.07
    Sn
    -0.07
    _ENGINE
    -0.06
    Stamped
    -0.06
    orr
    -0.06
    ichen
    -0.06
    rous
    -0.06
    iez
    -0.06
    POSITIVE LOGITS
     distortion
    0.07
    MATRIX
    0.07
    运
    0.06
    antine
    0.06
     мире
    0.06
     Contribution
    0.06
    -widgets
    0.06
     heaters
    0.06
     invo
    0.06
     soon
    0.06
    Act Density 0.122%

    No Known Activations