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

    Neuronpedia

    INDEX
    Explanations

    -Identifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doll
    -0.08
    deps
    -0.07
    publish
    -0.07
     seçenek
    -0.07
    trans
    -0.07
    oň
    -0.06
    eel
    -0.06
     Phoenix
    -0.06
    国
    -0.06
    okable
    -0.06
    POSITIVE LOGITS
     affects
    0.07
     své
    0.07
    approximately
    0.06
     solve
    0.06
     VAN
    0.06
     putting
    0.06
    每
    0.06
     PTR
    0.06
     حاصل
    0.06
     Until
    0.06
    Act Density 0.000%

    No Known Activations