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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hotspot
    -0.07
     Крас
    -0.07
     двох
    -0.07
     payroll
    -0.06
    NSS
    -0.06
     _____
    -0.06
    Southern
    -0.06
     \""
    -0.06
    cation
    -0.06
     Roh
    -0.06
    POSITIVE LOGITS
    ็ว
    0.07
    indsight
    0.07
     experience
    0.07
    (';
    0.07
     ldap
    0.06
    ิงห
    0.06
     इन
    0.06
    -sized
    0.06
     cập
    0.06
    -padding
    0.06
    Act Density 0.022%

    No Known Activations