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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trophic
    0.81
     insults
    0.80
     crescendo
    0.78
     carnage
    0.75
     disillusion
    0.75
     dislikes
    0.74
     steroids
    0.74
     flanges
    0.73
     morphogenesis
    0.71
     baits
    0.71
    POSITIVE LOGITS
     JK
    0.88
    Java
    0.87
    L
    0.85
     LN
    0.84
     Java
    0.82
    Pem
    0.81
    D
    0.78
     JC
    0.78
     JM
    0.78
     LSP
    0.78
    Act Density 0.002%

    No Known Activations