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

    Neuronpedia

    INDEX
    Explanations

    contact information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＆
    -0.07
     आकर
    -0.06
    주시
    -0.06
    암
    -0.06
    .CG
    -0.06
    >Your
    -0.06
     örgüt
    -0.06
    .snp
    -0.06
    _MIX
    -0.06
    _plugins
    -0.06
    POSITIVE LOGITS
    (outputs
    0.07
     attire
    0.07
    -playing
    0.07
     positively
    0.07
    ेष
    0.06
     남자
    0.06
     sacrificed
    0.06
     initialState
    0.06
     شیر
    0.06
     men
    0.06
    Act Density 0.008%

    No Known Activations