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

    Neuronpedia

    INDEX
    Explanations

    code instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ほん
    -0.08
    ajor
    -0.08
    minor
    -0.07
     querida
    -0.07
     стали
    -0.07
     equality
    -0.07
     côt
    -0.07
    Equality
    -0.07
     hockey
    -0.07
     धन
    -0.07
    POSITIVE LOGITS
     Clearing
    0.13
    _reset
    0.13
     resetting
    0.13
    -reset
    0.13
    .clear
    0.12
     અગાઉ
    0.12
     очищ
    0.12
    Previous
    0.12
     очист
    0.12
     previous
    0.12
    Act Density 0.011%

    No Known Activations