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

    Neuronpedia

    INDEX
    Explanations

    discussions/explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wrap
    -0.07
     corners
    -0.06
    _PLAYER
    -0.06
     deficiencies
    -0.06
    (domain
    -0.06
    produto
    -0.06
     discredit
    -0.06
     Bridge
    -0.06
    ')
↵
    -0.05
    $/
    -0.05
    POSITIVE LOGITS
    350
    0.08
    _CUSTOM
    0.07
    341
    0.07
     웹사이트
    0.07
    ops
    0.07
     philippines
    0.06
     Michele
    0.06
    циклоп
    0.06
    .frame
    0.06
     Frames
    0.06
    Act Density 0.284%

    No Known Activations