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

    Neuronpedia

    INDEX
    Explanations

    negative or avoiding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eradic
    0.54
     shady
    0.50
     comedic
    0.49
     anecd
    0.48
     fanáticos
    0.48
     Ehrlich
    0.48
     mecan
    0.48
     alveolar
    0.48
     curve
    0.47
     tact
    0.46
    POSITIVE LOGITS
    แมนเชสเตอร์ซิตี
    0.50
    फल
    0.46
    ARI
    0.46
    OSS
    0.46
    sning
    0.46
    शिला
    0.46
    IN
    0.45
    Fuse
    0.45
    Placement
    0.43
    getQuery
    0.43
    Act Density 0.000%

    No Known Activations