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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restau
    -0.07
     discrimin
    -0.07
    endir
    -0.06
    _contains
    -0.06
     aus
    -0.06
     Grow
    -0.06
    prend
    -0.06
    -0.06
     olig
    -0.06
     layered
    -0.06
    POSITIVE LOGITS
     scenes
    0.07
     appro
    0.06
    ph
    0.06
    šní
    0.06
     Deb
    0.06
     prone
    0.06
     Serial
    0.06
    CHAN
    0.06
    _bucket
    0.06
     Premiership
    0.06
    Act Density 0.003%

    No Known Activations