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

    Neuronpedia

    INDEX
    Explanations

    Compare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEPTH
    -0.06
     dumps
    -0.06
     reimbursement
    -0.06
    -keys
    -0.06
     cancell
    -0.06
     execute
    -0.06
     through
    -0.06
    pute
    -0.06
    -enter
    -0.06
    iphers
    -0.06
    POSITIVE LOGITS
     schl
    0.07
     unfolds
    0.06
     MAG
    0.06
    (addr
    0.06
     gấp
    0.06
    음
    0.06
     좋아
    0.06
    मन
    0.06
    的情况
    0.06
     برج
    0.06
    Act Density 0.020%

    No Known Activations