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

    Neuronpedia

    INDEX
    Explanations

    Artificial intelligence/learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิโ
    -0.07
    ό
    -0.07
    豆
    -0.07
    НІ
    -0.06
    dap
    -0.06
     spre
    -0.06
    _semaphore
    -0.06
    .disabled
    -0.06
    /stretch
    -0.06
    _EL
    -0.06
    POSITIVE LOGITS
    aybe
    0.07
     hr
    0.07
     physique
    0.07
    Massage
    0.07
     Graham
    0.07
    UBLIC
    0.06
    uggested
    0.06
     maize
    0.06
    	glog
    0.06
     CreateTable
    0.06
    Act Density 0.030%

    No Known Activations