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

    Neuronpedia

    INDEX
    Explanations

    origin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strings
    -0.07
     identities
    -0.06
     goats
    -0.06
    @Id
    -0.06
    pcodes
    -0.06
     relied
    -0.06
    (instruction
    -0.06
     digit
    -0.06
    /cm
    -0.06
    CustomLabel
    -0.06
    POSITIVE LOGITS
     refurb
    0.07
    .parseFloat
    0.07
    Thread
    0.06
    нем
    0.06
    ��
    0.06
    _sparse
    0.06
     edilmiş
    0.06
     Secret
    0.06
    Meanwhile
    0.06
     amacıyla
    0.06
    Act Density 0.000%

    No Known Activations