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

    Neuronpedia

    INDEX
    Explanations

    Travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rejected
    -0.07
    .Media
    -0.07
    .q
    -0.07
     mell
    -0.07
     DAR
    -0.06
     Roo
    -0.06
    _ak
    -0.06
    mast
    -0.06
    dan
    -0.06
    .with
    -0.06
    POSITIVE LOGITS
     """
↵
↵
    0.07
    город
    0.06
    opcode
    0.06
     ifdef
    0.06
    ської
    0.06
    _use
    0.06
     each
    0.06
    meaning
    0.06
    ностей
    0.06
     अत
    0.06
    Act Density 0.028%

    No Known Activations