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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NEED
    -0.07
     citations
    -0.07
     hesitation
    -0.07
     Wish
    -0.06
     Cancel
    -0.06
    Permissions
    -0.06
    Protected
    -0.06
     suspense
    -0.06
     Eff
    -0.06
     cheers
    -0.06
    POSITIVE LOGITS
    áte
    0.07
     CNC
    0.06
     örgüt
    0.06
    tle
    0.06
     stál
    0.06
     naval
    0.06
     CLIIIK
    0.06
    aver
    0.06
     перев
    0.06
     گذاری
    0.06
    Act Density 0.048%

    No Known Activations