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

    Neuronpedia

    INDEX
    Explanations

    Code and commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (combo
    -0.08
     sofas
    -0.08
     tern
    -0.07
     Tik
    -0.07
     πο
    -0.07
    _moves
    -0.07
     Tuesdays
    -0.07
     locom
    -0.07
     Instagram
    -0.07
     propulsion
    -0.07
    POSITIVE LOGITS
    Issuer
    0.12
     issuance
    0.12
     certificate
    0.11
     issuer
    0.11
    Certificate
    0.11
    certificate
    0.11
    .Certificate
    0.11
    هادة
    0.10
     certificates
    0.10
    issuer
    0.10
    Act Density 0.004%

    No Known Activations