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

    Neuronpedia

    INDEX
    Explanations

    _box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΟΛ
    -0.07
    -----------
↵
    -0.07
     PHYS
    -0.06
    Death
    -0.06
     kotlinx
    -0.06
     Attacks
    -0.06
     जन
    -0.06
     formidable
    -0.06
    .responses
    -0.06
    ictureBox
    -0.06
    POSITIVE LOGITS
    609
    0.07
    821
    0.07
    nell
    0.07
     pooling
    0.06
    oscope
    0.06
     leveling
    0.06
    Mui
    0.06
    thermal
    0.06
    349
    0.06
     Carson
    0.06
    Act Density 0.000%

    No Known Activations