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

    Neuronpedia

    INDEX
    Explanations

    varied text types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Paths
    -0.06
    HIP
    -0.06
     lookahead
    -0.06
    rd
    -0.06
    peng
    -0.06
    Scope
    -0.06
     Pride
    -0.06
     Aydın
    -0.06
     sesame
    -0.06
     зах
    -0.06
    POSITIVE LOGITS
     late
    0.08
     migrate
    0.07
     conservative
    0.07
     pricing
    0.07
    administrator
    0.07
     prom
    0.07
    Independ
    0.06
    /classes
    0.06
     yield
    0.06
     Maria
    0.06
    Act Density 0.000%

    No Known Activations