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

    Neuronpedia

    INDEX
    Explanations

    90s numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Numbers
    -0.08
    ené
    -0.07
    (vertical
    -0.07
     policies
    -0.07
     PropertyValue
    -0.07
     صالح
    -0.06
    eld
    -0.06
    projection
    -0.06
     ettiği
    -0.06
     regarded
    -0.06
    POSITIVE LOGITS
     Credential
    0.06
    ogra
    0.06
    WRITE
    0.06
    _BLOCK
    0.06
    StackNavigator
    0.06
     su
    0.06
    axon
    0.05
     btnCancel
    0.05
     "'";↵
    0.05
     Suarez
    0.05
    Act Density 0.007%

    No Known Activations