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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Se
    -0.08
    _DBG
    -0.08
     Restrictions
    -0.08
    Couldn't
    -0.08
     کیلئے
    -0.07
     quotas
    -0.07
    uelve
    -0.07
    ual
    -0.07
    ográ
    -0.07
     dibanding
    -0.07
    POSITIVE LOGITS
    .employee
    0.08
     कर्मचारी
    0.08
     arches
    0.08
     repetitions
    0.08
    .emp
    0.07
    employees
    0.07
    .Employee
    0.07
    .soap
    0.07
     Stark
    0.07
     hor
    0.07
    Act Density 0.003%

    No Known Activations