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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reimbursement
    -0.09
    .Login
    -0.09
    Credential
    -0.09
    credential
    -0.09
     racont
    -0.09
     ट्विटर
    -0.08
     reimburse
    -0.08
     reins
    -0.08
    Credentials
    -0.08
     қоғам
    -0.08
    POSITIVE LOGITS
     ripping
    0.09
     scissors
    0.09
     cutter
    0.09
     punches
    0.09
     markings
    0.09
     sharper
    0.09
     commanded
    0.08
     Kirk
    0.08
     cuts
    0.08
     нож
    0.08
    Act Density 0.013%

    No Known Activations