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

    Neuronpedia

    INDEX
    Explanations

    help and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ..↵
    -0.07
     ambiente
    -0.07
    下的
    -0.06
    __));↵
    -0.06
     arbitration
    -0.06
     Xia
    -0.06
     ;↵↵
    -0.06
    groups
    -0.06
    )")↵↵
    -0.06
     Pé
    -0.06
    POSITIVE LOGITS
    /Instruction
    0.07
     augment
    0.06
    (integer
    0.06
     gesture
    0.06
     pojist
    0.06
     Flip
    0.06
     inhibited
    0.06
    aising
    0.06
    […
    0.06
    опрос
    0.06
    Act Density 0.350%

    No Known Activations