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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Boolean
    -0.07
    �
    -0.07
     attract
    -0.06
     хлоп
    -0.06
     hiking
    -0.06
     sebuah
    -0.06
     repell
    -0.06
     สาข
    -0.06
     occurrences
    -0.06
    <this
    -0.06
    POSITIVE LOGITS
    -
    0.07
    Capability
    0.07
     roky
    0.06
    山
    0.06
     Erotische
    0.06
    Mine
    0.06
    _]
    0.06
    Vm
    0.06
    дяки
    0.06
    ически
    0.06
    Act Density 0.000%

    No Known Activations