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

    Neuronpedia

    INDEX
    Explanations

    hostnames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retract
    -0.09
     couples
    -0.09
     marriages
    -0.08
     confined
    -0.07
     만
    -0.07
     conjoint
    -0.07
     Couples
    -0.07
    hol
    -0.07
     territorial
    -0.07
    (Re
    -0.07
    POSITIVE LOGITS
    .hostname
    0.10
     hostname
    0.10
     localhost
    0.09
    localhost
    0.09
    /network
    0.09
    _hostname
    0.08
     ішінде
    0.08
     hosts
    0.08
    =device
    0.08
    hostname
    0.08
    Act Density 0.008%

    No Known Activations