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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     บ
    -0.07
     Joan
    -0.07
     worldly
    -0.07
     userdata
    -0.07
     tiêu
    -0.07
    大き
    -0.07
     cocktails
    -0.07
     latitude
    -0.06
    .Verify
    -0.06
    esus
    -0.06
    POSITIVE LOGITS
    extract
    0.06
    .model
    0.06
     resulting
    0.06
    /Create
    0.06
     Bachelor
    0.06
    ql
    0.06
    Cycle
    0.06
    _SUBJECT
    0.06
    -he
    0.06
    .execute
    0.06
    Act Density 0.040%

    No Known Activations