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

    Neuronpedia

    INDEX
    Explanations

    heap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parole
    -0.06
     Somerset
    -0.06
    -wheel
    -0.06
    ROPERTY
    -0.06
    /mol
    -0.06
     Devils
    -0.06
    parallel
    -0.06
    �
    -0.06
    "]
    -0.06
    }}"
    -0.06
    POSITIVE LOGITS
     jednodu
    0.07
     gag
    0.06
    ulsion
    0.06
    >tagger
    0.06
    038
    0.06
    фор
    0.06
    angles
    0.06
    (Property
    0.06
     phút
    0.06
    uggested
    0.06
    Act Density 0.000%

    No Known Activations