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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     })
↵
    -0.07
     Adapt
    -0.06
     Buildings
    -0.06
     potom
    -0.06
     Hook
    -0.06
     therapists
    -0.05
     surround
    -0.05
    lems
    -0.05
     ves
    -0.05
    otate
    -0.05
    POSITIVE LOGITS
     ply
    0.07
     контролю
    0.07
    (flags
    0.06
    indic
    0.06
     circumstance
    0.06
     اض
    0.06
    О
    0.06
    _task
    0.06
    魯
    0.06
     розп
    0.06
    Act Density 0.000%

    No Known Activations