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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    telefono
    -0.07
    byn
    -0.07
    	Error
    -0.07
     Parties
    -0.07
     Saving
    -0.06
     Savings
    -0.06
    Special
    -0.06
    Photos
    -0.06
     […]
    -0.06
    .Media
    -0.06
    POSITIVE LOGITS
    _AUD
    0.07
    implicitly
    0.06
     QU
    0.06
    。。
    0.06
     بدان
    0.06
    дав
    0.06
     Removing
    0.06
    呈
    0.06
    IDL
    0.06
    .DataGridViewContentAlignment
    0.06
    Act Density 0.011%

    No Known Activations