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

    Neuronpedia

    INDEX
    Explanations

    words followed by related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reporters
    -0.94
     Advertisements
    -0.82
     Portugu
    -0.82
     lemn
    -0.82
     Flüssigkeit
    -0.82
     guerres
    -0.80
     bacterias
    -0.80
     ralla
    -0.79
     pistons
    -0.78
    niana
    -0.77
    POSITIVE LOGITS
    Iam
    0.87
    獺
    0.87
    campo
    0.86
    crunch
    0.79
    sApp
    0.77
    bof
    0.77
    ❸
    0.76
     masking
    0.76
    довых
    0.75
     AutoMapper
    0.75
    Act Density 0.000%

    No Known Activations