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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defiant
    -0.06
     Moving
    -0.06
     moving
    -0.06
    apters
    -0.06
     SSP
    -0.06
    rch
    -0.06
    _properties
    -0.06
    indices
    -0.06
    ered
    -0.06
    erring
    -0.06
    POSITIVE LOGITS
    ंगल
    0.07
     AtomicInteger
    0.07
    dispatch
    0.07
    لاث
    0.06
    atchet
    0.06
     اینتر
    0.06
     Amateur
    0.06
     CURLOPT
    0.06
    ализации
    0.06
    _PARAM
    0.06
    Act Density 0.002%

    No Known Activations