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

    Neuronpedia

    INDEX
    Explanations

    technical writing excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Expr
    -0.06
    _folders
    -0.06
     Scaffold
    -0.06
    hashCode
    -0.06
     Ct
    -0.06
    	resource
    -0.06
    getResponse
    -0.06
    _per
    -0.06
    clus
    -0.06
    POSITIVE LOGITS
    NR
    0.07
    嗯
    0.07
    utting
    0.06
     ihtiyac
    0.06
     Avalanche
    0.06
    >>,
    0.06
    indow
    0.06
     bursting
    0.06
    {@
    0.06
    anas
    0.06
    Act Density 0.205%

    No Known Activations