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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    萳
    -0.07
    Decode
    -0.07
    滃
    -0.07
    Cannot
    -0.07
    :')
    -0.06
    �断
    -0.06
     Cancel
    -0.06
    Sweet
    -0.06
    ANNOT
    -0.06
    MARK
    -0.06
    POSITIVE LOGITS
     working
    0.08
    _arch
    0.07
    적인
    0.07
     causa
    0.06
     latch
    0.06
    /meta
    0.06
    .Kind
    0.06
    (access
    0.06
    OLUM
    0.06
    .contact
    0.06
    Act Density 0.010%

    No Known Activations