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

    Neuronpedia

    INDEX
    Explanations

    achieving goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Chat
    -0.07
    ilded
    -0.06
    tt
    -0.06
     quotid
    -0.06
     family
    -0.06
    <td
    -0.06
    egade
    -0.06
     comprom
    -0.06
     membres
    -0.06
    чить
    -0.06
    POSITIVE LOGITS
     UIAlertController
    0.07
    _processes
    0.06
     spyOn
    0.06
    луж
    0.06
    (Keys
    0.06
     Unix
    0.06
     Naples
    0.06
    _LABEL
    0.06
     homelessness
    0.06
     Vertex
    0.06
    Act Density 0.084%

    No Known Activations