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

    Neuronpedia

    INDEX
    Explanations

    react code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     כך
    0.76
    كتر
    0.71
     Preventing
    0.70
    уда
    0.67
     Basic
    0.66
     JCV
    0.64
     Focus
    0.63
    рд
    0.63
    мова
    0.63
     HRV
    0.63
    POSITIVE LOGITS
     distingue
    0.78
     vienen
    0.69
     diput
    0.66
    品种
    0.66
    azor
    0.65
    TREE
    0.65
     primeras
    0.64
    umbuhan
    0.64
    डून
    0.63
     professe
    0.63
    Act Density 0.052%

    No Known Activations