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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fisher
    -0.80
    덜
    -0.67
     Fish
    -0.64
    fishes
    -0.64
    Fisher
    -0.62
    FISH
    -0.62
     Fischer
    -0.61
     fish
    -0.58
     a
    -0.56
     za
    -0.56
    POSITIVE LOGITS
     itſelf
    1.10
     myſelf
    0.89
     greateſt
    0.87
     Jefus
    0.86
     raiſ
    0.85
     Houſe
    0.85
     Theſe
    0.85
     Efq
    0.84
    ſelves
    0.84
     ſche
    0.84
    Act Density 0.110%

    No Known Activations