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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _out
    -0.07
    .Button
    -0.07
     iPad
    -0.06
    Employee
    -0.06
     deposition
    -0.06
    uploader
    -0.06
     Securities
    -0.06
     Translator
    -0.06
    _member
    -0.06
     ARC
    -0.06
    POSITIVE LOGITS
    imizeBox
    0.07
     très
    0.06
    uhe
    0.06
     trump
    0.06
    irit
    0.06
     журн
    0.06
     نموده
    0.06
    456
    0.06
    ुबह
    0.06
     hudeb
    0.06
    Act Density 0.036%

    No Known Activations