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

    Neuronpedia

    INDEX
    Explanations

    surfactants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bites
    -0.06
    话
    -0.06
     hoops
    -0.06
     Reputation
    -0.06
     Charges
    -0.06
    Pear
    -0.06
     Climate
    -0.06
     decir
    -0.06
     hole
    -0.06
     kode
    -0.06
    POSITIVE LOGITS
    stdin
    0.07
     Holden
    0.07
    eln
    0.07
    QN
    0.07
    &T
    0.06
    ANT
    0.06
     ck
    0.06
    anka
    0.06
     =>
    0.06
    ekte
    0.06
    Act Density 0.004%

    No Known Activations