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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conse
    -0.08
     clarification
    -0.08
     equation
    -0.08
     list
    -0.07
     Equation
    -0.07
     calculus
    -0.07
     Duration
    -0.07
     with
    -0.07
     Huang
    -0.07
     statement
    -0.07
    POSITIVE LOGITS
     dormant
    0.15
     भीतर
    0.14
     latent
    0.14
     নিহ
    0.14
     instincts
    0.13
     внутри
    0.13
     ভিত
    0.13
     अंदर
    0.13
     awakened
    0.13
     lurking
    0.13
    Act Density 0.134%

    No Known Activations