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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    twimg
    -0.68
    }]
    -0.60
    __':
    -0.59
    __(/*!
    -0.59
    }],
    -0.58
    TagHelper
    -0.55
    VIAF
    -0.55
    __":
    -0.55
    }))
    -0.54
    __':
    -0.52
    POSITIVE LOGITS
     utafitiHapana
    0.57
    市镇
    0.54
    liflower
    0.52
    getTransaction
    0.52
    rze
    0.52
     POND
    0.45
    putan
    0.44
     cabe
    0.44
    iseks
    0.43
    isContained
    0.42
    Act Density 0.001%

    No Known Activations