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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [$
    -0.07
    _activate
    -0.07
     utiliza
    -0.07
     Holly
    -0.07
     -$
    -0.07
    +='
    -0.07
    (left
    -0.07
    ]<<"
    -0.07
    คว
    -0.06
    衣服
    -0.06
    POSITIVE LOGITS
     glean
    0.06
    .getvalue
    0.06
    Airport
    0.06
     issuer
    0.06
    させ
    0.06
     κρα
    0.06
    gne
    0.05
     Tanks
    0.05
     club
    0.05
     gren
    0.05
    Act Density 0.289%

    No Known Activations