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

    Neuronpedia

    INDEX
    Explanations

    Thumb and fingers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .jpeg
    -0.06
     dumb
    -0.06
     AW
    -0.06
     قط
    -0.06
     İli
    -0.06
    彻
    -0.06
    Ip
    -0.06
     парт
    -0.06
    ANC
    -0.06
    Professor
    -0.06
    POSITIVE LOGITS
     filename
    0.06
    lerinin
    0.06
    -hole
    0.06
     defenses
    0.06
    nat
    0.06
     shear
    0.06
    caster
    0.06
     haunt
    0.06
     defense
    0.06
    plorer
    0.06
    Act Density 0.008%

    No Known Activations