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

    Neuronpedia

    INDEX
    Explanations

    Paleolithic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Christina
    -0.10
     megl
    -0.08
    Julia
    -0.08
     Julia
    -0.08
     hateful
    -0.08
    kes
    -0.08
     hake
    -0.08
     stiffness
    -0.08
     görmek
    -0.07
     integrity
    -0.07
    POSITIVE LOGITS
     societies
    0.10
    -era
    0.09
    面对
    0.08
     aston
    0.08
     civilization
    0.08
     instincts
    0.08
     sedent
    0.08
    irement
    0.08
     সভ
    0.08
    文明
    0.08
    Act Density 0.013%

    No Known Activations