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

    Neuronpedia

    INDEX
    Explanations

    exaggerating, forcing, imagining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ktional
    0.38
    asim
    0.36
     पारंपरिक
    0.35
     FCC
    0.35
    ON
    0.35
    OP
    0.34
     EEOC
    0.34
     neutrophil
    0.33
     blender
    0.33
    asonic
    0.33
    POSITIVE LOGITS
     или
    0.49
     veya
    0.48
     alebo
    0.48
     અથવા
    0.46
     prea
    0.41
     ή
    0.41
    或
    0.41
     அல்லது
    0.40
     או
    0.40
     murders
    0.40
    Act Density 0.125%

    No Known Activations