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

    Neuronpedia

    INDEX
    Explanations

    sentences where someone includes a caveat or expresses uncertainty

    oai_token-act-pair · gemini-2.0-flash

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.68
    HasAnnotation
    -0.65
     kasarigan
    -0.64
     Mérimée
    -0.60
    --){
    -0.53
    pite
    -0.53
    uros
    -0.52
    EndContext
    -0.52
     onView
    -0.51
    RequiresApi
    -0.51
    POSITIVE LOGITS
    AccessorTable
    0.82
    antMatchers
    0.60
    localctx
    0.51
     mapStateToProps
    0.51
     neceff
    0.50
     <<<<<<<<<<<<<<
    0.50
    AutoScaleMode
    0.49
     nahilalakip
    0.47
     reafon
    0.47
     chofe
    0.47
    Act Density 5.937%

    No Known Activations