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

    Neuronpedia

    INDEX
    Explanations

    NPR reporter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.78
     I
    0.69
     Stripes
    0.68
    ik
    0.67
    ం
    0.64
    ץ
    0.64
     Arma
    0.63
     Mirage
    0.63
    Innovative
    0.63
    夗
    0.61
    POSITIVE LOGITS
    ли
    0.75
    л
    0.69
    ја
    0.66
    annya
    0.64
     costi
    0.64
    sw
    0.61
     shock
    0.60
     طریقے
    0.60
     clínico
    0.60
    t
    0.59
    Act Density 0.000%

    No Known Activations