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

    Neuronpedia

    INDEX
    Explanations

    reluctantly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Enter
    -0.07
    ancellable
    -0.06
     kriz
    -0.06
     dipped
    -0.06
    able
    -0.06
     caffe
    -0.06
    Cells
    -0.06
     prostit
    -0.06
    derive
    -0.06
     있는
    -0.06
    POSITIVE LOGITS
     reluctant
    0.14
     reluctantly
    0.12
     reluctance
    0.12
     unwilling
    0.08
    契
    0.07
    ВА
    0.07
     emotionally
    0.07
     recruited
    0.06
    爱
    0.06
     Bengal
    0.06
    Act Density 0.009%

    No Known Activations