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

    Neuronpedia

    INDEX
    Explanations

    ica

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Experience
    -0.07
    fers
    -0.07
     seeming
    -0.06
     Estimates
    -0.06
    bb
    -0.06
    Ability
    -0.06
    Absolute
    -0.06
    balance
    -0.06
     ارسال
    -0.06
    fo
    -0.06
    POSITIVE LOGITS
    IONS
    0.07
    _SPELL
    0.07
     hacker
    0.07
    _LOCK
    0.07
     Kız
    0.07
     Grill
    0.07
    reffen
    0.06
     Latinos
    0.06
     thỏa
    0.06
    oundation
    0.06
    Act Density 0.000%

    No Known Activations