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

    Neuronpedia

    INDEX
    Explanations

    meet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billionaires
    -0.08
    і
    -0.06
    	part
    -0.06
    Songs
    -0.06
     dame
    -0.06
    _impl
    -0.06
     went
    -0.06
     Polymer
    -0.06
     θεω
    -0.06
     oxide
    -0.06
    POSITIVE LOGITS
    ync
    0.07
     ).↵↵
    0.07
    nown
    0.07
     jTextField
    0.06
     conventions
    0.06
     impossible
    0.06
    _WATCH
    0.06
    ステム
    0.06
    %.↵
    0.06
    !.↵↵
    0.06
    Act Density 0.018%

    No Known Activations