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

    Neuronpedia

    INDEX
    Explanations

    by default or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aide
    0.44
     Vault
    0.39
     GestureDetector
    0.36
    াৎ
    0.36
     ◇
    0.36
     vaults
    0.34
    比賽
    0.34
     Kontak
    0.34
    腮
    0.34
     लगे
    0.33
    POSITIVE LOGITS
    zantine
    0.96
     virtue
    0.86
     dint
    0.71
     way
    0.64
    rne
    0.64
    衷
    0.64
    zant
    0.63
     means
    0.63
     conséquent
    0.56
    ronic
    0.55
    Act Density 0.028%

    No Known Activations