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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     molec
    -0.07
    вич
    -0.07
     beads
    -0.07
     Information
    -0.06
     spoil
    -0.06
    =Value
    -0.06
     Memor
    -0.06
     Clips
    -0.06
    Header
    -0.06
     horror
    -0.06
    POSITIVE LOGITS
     až
    0.08
    폭
    0.08
     якості
    0.07
    empor
    0.07
     verdade
    0.07
    ाइम
    0.06
    compiler
    0.06
    .visitMethodInsn
    0.06
    pora
    0.06
     사
    0.06
    Act Density 0.104%

    No Known Activations