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

    Neuronpedia

    INDEX
    Explanations

    persuasion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     form
    -0.08
    Testing
    -0.07
    公式
    -0.06
     forms
    -0.06
     convergence
    -0.06
     Guardians
    -0.06
    _buffer
    -0.06
    /IP
    -0.06
     astronomical
    -0.06
     forum
    -0.06
    POSITIVE LOGITS
     convince
    0.11
     persuaded
    0.08
     convinced
    0.07
     persuade
    0.07
    vang
    0.07
     rozhod
    0.07
    esidir
    0.07
    _than
    0.06
    ither
    0.06
     Jess
    0.06
    Act Density 0.021%

    No Known Activations