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

    Neuronpedia

    INDEX
    Explanations

    /plain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uniform
    -0.07
    )){
↵
    -0.07
     evrop
    -0.07
    角色
    -0.07
     идет
    -0.07
    istry
    -0.06
    Associ
    -0.06
     itching
    -0.06
    수를
    -0.06
    (control
    -0.06
    POSITIVE LOGITS
    /plain
    0.14
     compliance
    0.06
    ава
    0.06
    يون
    0.06
    ataires
    0.06
     diverted
    0.06
    large
    0.06
     mdb
    0.06
    ewood
    0.06
    Captain
    0.06
    Act Density 0.000%

    No Known Activations