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

    Neuronpedia

    INDEX
    Explanations

    separately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oke
    -0.07
    .avg
    -0.07
     kanı
    -0.06
    .showMessage
    -0.06
    inus
    -0.06
    ículos
    -0.06
    _owner
    -0.06
     rebound
    -0.06
    _WEB
    -0.06
     flows
    -0.06
    POSITIVE LOGITS
     separately
    0.14
     individually
    0.09
    $ar
    0.06
    -wise
    0.06
     já
    0.06
    새
    0.06
     anders
    0.06
     sexuality
    0.06
    �
    0.06
     Personal
    0.06
    Act Density 0.005%

    No Known Activations