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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ehicle
    -0.07
    	lock
    -0.07
    .right
    -0.07
    .priority
    -0.07
     Exec
    -0.07
     Risk
    -0.07
     mortgage
    -0.07
     militant
    -0.06
    μβ
    -0.06
    _pt
    -0.06
    POSITIVE LOGITS
    역
    0.06
     canActivate
    0.06
    _ls
    0.06
    fel
    0.06
    Animated
    0.06
    "http
    0.06
    �
    0.06
    διά
    0.06
    Disclaimer
    0.06
     impres
    0.05
    Act Density 0.067%

    No Known Activations