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

    Neuronpedia

    INDEX
    Explanations

    neuroscience research methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ozo
    -0.07
     invariant
    -0.06
     kube
    -0.06
     Joh
    -0.06
     Guth
    -0.06
    acin
    -0.06
    istik
    -0.06
     relief
    -0.06
     rew
    -0.06
    -memory
    -0.05
    POSITIVE LOGITS
    .consumer
    0.07
    ityEngine
    0.06
    emy
    0.06
    /Internal
    0.06
    nostic
    0.06
    	stats
    0.06
    áž
    0.06
     pinterest
    0.06
    urrect
    0.06
    stateParams
    0.06
    Act Density 0.004%

    No Known Activations