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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =params
    -0.08
    ങ്ങളിലും
    -0.07
     mingle
    -0.07
    .presenter
    -0.07
     initiatives
    -0.07
    =config
    -0.07
     boys
    -0.07
     台
    -0.07
     Corey
    -0.07
     donation
    -0.07
    POSITIVE LOGITS
    ertal
    0.08
    lego
    0.08
     сақтау
    0.08
    odne
    0.08
    anova
    0.08
     nästan
    0.08
    -eb
    0.08
     plur
    0.07
    anking
    0.07
     evrops
    0.07
    Act Density 0.010%

    No Known Activations