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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favour
    -0.06
     HQ
    -0.06
    _storage
    -0.06
    HC
    -0.06
    -Y
    -0.06
    brightness
    -0.06
     victim
    -0.06
     might
    -0.06
    -sensitive
    -0.06
     cursed
    -0.06
    POSITIVE LOGITS
    .SetBool
    0.07
    .StatusBadRequest
    0.07
    .OneToOne
    0.07
     :|:
    0.07
    assertCount
    0.07
    ('.')[
    0.07
     hmot
    0.07
    津
    0.07
     RelayCommand
    0.07
    듯
    0.07
    Act Density 0.022%

    No Known Activations