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

    Neuronpedia

    INDEX
    Explanations

    specific instructions or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lowers
    0.42
     vibrates
    0.41
     scissor
    0.41
     enables
    0.41
     scallop
    0.41
     getNodeId
    0.40
     austenitic
    0.40
     Scotia
    0.40
     Mors
    0.40
    Finland
    0.39
    POSITIVE LOGITS
    bal
    0.48
     acerc
    0.44
    část
    0.44
     näher
    0.43
    ipan
    0.43
    たち
    0.43
    তায়
    0.42
     parte
    0.42
    in
    0.42
    ઠા
    0.42
    Act Density 0.004%

    No Known Activations