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

    Neuronpedia

    INDEX
    Explanations

    Java database connectivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loses
    -0.07
     episodes
    -0.07
    	print
    -0.06
     differs
    -0.06
     constr
    -0.06
     silent
    -0.06
    Ark
    -0.06
     vợ
    -0.06
     reimbursement
    -0.06
     Evalu
    -0.06
    POSITIVE LOGITS
     viewport
    0.07
    CLLocation
    0.07
    .comp
    0.07
    _bw
    0.07
    ظٹ
    0.06
    untu
    0.06
    known
    0.06
    áme
    0.06
    embers
    0.06
    annabin
    0.06
    Act Density 0.032%

    No Known Activations