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

    Neuronpedia

    INDEX
    Explanations

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PAL
    -0.07
     locate
    -0.06
     attacked
    -0.06
    rics
    -0.06
     Games
    -0.06
     optics
    -0.06
    _sol
    -0.06
    武
    -0.06
    SEQU
    -0.06
    .sol
    -0.05
    POSITIVE LOGITS
    Vm
    0.07
    Emer
    0.07
     prac
    0.07
    omination
    0.07
     Comb
    0.07
     esas
    0.07
    Jane
    0.06
     Fresh
    0.06
     üy
    0.06
    getConnection
    0.06
    Act Density 0.029%

    No Known Activations