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

    Neuronpedia

    INDEX
    Explanations

    ice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stadium
    -0.07
    之后
    -0.06
    금
    -0.06
     endorsements
    -0.06
    mus
    -0.06
     فارسی
    -0.06
     персп
    -0.06
    (types
    -0.06
     foss
    -0.06
     entail
    -0.06
    POSITIVE LOGITS
    .",
↵
    0.07
     Dave
    0.07
     dve
    0.07
     Lov
    0.07
    .best
    0.06
     Heal
    0.06
     RC
    0.06
    Spr
    0.06
     Company
    0.06
    |;↵
    0.06
    Act Density 0.002%

    No Known Activations