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

    Neuronpedia

    INDEX
    Explanations

    bitter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propensity
    -0.08
    ील
    -0.07
     Secretariat
    -0.07
    -ST
    -0.07
    WS
    -0.07
     perfor
    -0.07
     Hanover
    -0.07
     collapsing
    -0.07
    -AS
    -0.07
     Running
    -0.07
    POSITIVE LOGITS
     bitterness
    0.13
     bitter
    0.12
     bitters
    0.10
    苦
    0.10
     disappointment
    0.09
     amarga
    0.09
     ụtọ
    0.09
    േദ
    0.09
     tones
    0.09
     محصول
    0.09
    Act Density 0.005%

    No Known Activations