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

    Neuronpedia

    INDEX
    Explanations

    incredible or amazing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poodle
    1.38
    학과
    1.31
    ன்
    1.28
     pouch
    1.28
     adage
    1.25
    م
    1.24
     storey
    1.23
    ung
    1.21
    は大
    1.21
    (/^
    1.20
    POSITIVE LOGITS
    OP
    1.36
    ulously
    1.33
    ą
    1.30
    namely
    1.28
    ly
    1.27
    lara
    1.27
    na
    1.26
    ں
    1.24
    nt
    1.23
    સ
    1.23
    Act Density 0.190%

    No Known Activations