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

    Neuronpedia

    INDEX
    Explanations

    ph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेशन
    -0.08
    always
    -0.07
    、これ
    -0.07
    bung
    -0.06
    ुच
    -0.06
     Loves
    -0.06
    Conversion
    -0.06
     felt
    -0.06
    riot
    -0.06
    peration
    -0.06
    POSITIVE LOGITS
    benhavn
    0.07
    ph
    0.07
    �p
    0.06
     repaired
    0.06
    #ab
    0.06
     ads
    0.06
     پایین
    0.06
     jewelry
    0.06
    bsd
    0.06
    `='$
    0.06
    Act Density 0.001%

    No Known Activations