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

    Neuronpedia

    INDEX
    Explanations

    β

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONNECTION
    -0.07
     QUEST
    -0.06
     humili
    -0.06
    _actions
    -0.06
    LETED
    -0.06
     temperament
    -0.06
     conqu
    -0.06
    -divider
    -0.06
    adge
    -0.06
     Legend
    -0.06
    POSITIVE LOGITS
    β
    0.07
    obia
    0.07
    eta
    0.07
    ');?></
    0.06
     β
    0.06
     stepped
    0.06
    beta
    0.06
     heated
    0.06
    -ab
    0.06
    45
    0.06
    Act Density 0.001%

    No Known Activations