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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     野
    -0.06
    metadata
    -0.06
     	↵
    -0.06
    ileges
    -0.06
     Charm
    -0.06
     GRAT
    -0.06
     Armor
    -0.06
    DAT
    -0.06
     LLP
    -0.06
    緊
    -0.06
    POSITIVE LOGITS
    ､:
    0.07
     Hai
    0.07
    	Mono
    0.07
    [s
    0.07
    (goal
    0.07
     apro
    0.06
    NgModule
    0.06
     olsa
    0.06
    .groupControl
    0.06
    海道
    0.06
    Act Density 0.006%

    No Known Activations