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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าส
    -0.07
     pulls
    -0.07
    'C
    -0.06
    'M
    -0.06
    )-
    -0.06
     offenses
    -0.06
    _scripts
    -0.06
     LW
    -0.06
    "indices
    -0.06
     Komment
    -0.06
    POSITIVE LOGITS
    ст
    0.07
    ود
    0.07
     variants
    0.06
     Kin
    0.06
    	create
    0.06
    classification
    0.06
    urgeon
    0.06
    .dsl
    0.06
    ucht
    0.06
    ongoose
    0.06
    Act Density 0.000%

    No Known Activations