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

    Neuronpedia

    INDEX
    Explanations

    09

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _topology
    -0.06
    tak
    -0.06
    Callbacks
    -0.06
    apore
    -0.06
    ban
    -0.06
    dna
    -0.06
    .ud
    -0.06
    RefreshLayout
    -0.06
     evils
    -0.06
    Singapore
    -0.06
    POSITIVE LOGITS
    .String
    0.07
     franç
    0.07
     прест
    0.07
     deform
    0.06
     Method
    0.06
    FFFFFF
    0.06
     which
    0.06
     вигляді
    0.06
     expectations
    0.06
     battling
    0.06
    Act Density 0.022%

    No Known Activations